SOTAVerified

Word Alignment

Word Alignment is the task of finding the correspondence between source and target words in a pair of sentences that are translations of each other.

Source: Neural Network-based Word Alignment through Score Aggregation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 551 papers

TitleStatusHype
Efficient Neural Machine Translation with Prior Word Alignment—0
Unsupervised Word Alignment via Cross-Lingual Contrastive LearningCode0
XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders—0
Subword Sampling for Low Resource Word Alignment—0
Mask-Align: Self-Supervised Neural Word AlignmentCode1
改善詞彙對齊以擷取片語翻譯之方法 (Improving Word Alignment for Extraction Phrasal Translation)—0
Alibaba Submission to the WMT20 Parallel Corpus Filtering Task—0
Unsupervised Cross-Lingual Part-of-Speech Tagging for Truly Low-Resource Scenarios—0
Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel CorporaCode1
Volctrans Parallel Corpus Filtering System for WMT 2020—0
FastEmit: Low-latency Streaming ASR with Sequence-level Emission RegularizationCode0
Counterfactual Variable Control for Robust and Interpretable Question AnsweringCode1
A Generalized Constraint Approach to Bilingual Dictionary Induction for Low-Resource Language Families—0
Constructing Uyghur Name Entity Recognition System using Neural Machine Translation Tag Projection—0
Generative latent neural models for automatic word alignment—0
Neural Baselines for Word Alignment—0
OpusFilter: A Configurable Parallel Corpus Filtering Toolbox—0
Learning aligned embeddings for semi-supervised word translation using Maximum Mean Discrepancy—0
Neural Simultaneous Speech Translation Using Alignment-Based Chunking—0
Evaluating Explanation Methods for Neural Machine Translation—0
Building an English-Chinese Parallel Corpus Annotated with Sub-sentential Translation Techniques—0
Line-a-line: A Tool for Annotating Word-Alignments—0
FrameNet Annotations Alignment using Attention-based Machine Translation—0
Automatic Construction of Aramaic-Hebrew Translation Lexicon—0
End-to-End Neural Word Alignment Outperforms GIZA++—0
Accurate Word Alignment Induction from Neural Machine TranslationCode0
Word Rotator's DistanceCode1
A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT—0
End-to-End Slot Alignment and Recognition for Cross-Lingual NLUCode1
Conversational Word Embedding for Retrieval-Based Dialog SystemCode1
Attention is Not Only a Weight: Analyzing Transformers with Vector NormsCode1
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized EmbeddingsCode1
A Simple Approach to Learning Unsupervised Multilingual Embeddings—0
On the Language Neutrality of Pre-trained Multilingual RepresentationsCode0
Locality Preserving Loss: Neighbors that Live together, Align together—0
Unsupervised Multilingual Alignment using Wasserstein BarycenterCode0
Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks—0
How Language-Neutral is Multilingual BERT?Code0
Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces—0
Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator—0
Essentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs—0
Annotated Guidelines and Building Reference Corpus for Myanmar-English Word Alignment—0
Jointly Learning to Align and Translate with Transformer ModelsCode0
Interconnecting lexical resources and word alignment: How do learners get on with particle verbs?—0
A Discriminative Neural Model for Cross-Lingual Word Alignment—0
Transformer-based Automatic Post-Editing with a Context-Aware Encoding Approach for Multi-Source Inputs—0
En-Ar Bilingual Word Embeddings without Word Alignment: Factors Effects—0
Learning Trilingual Dictionaries for Urdu -- Roman Urdu -- EnglishCode0
Bilingual Lexicon Induction through Unsupervised Machine TranslationCode0
Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language ModelsCode1
Show:102550
← PrevPage 3 of 12Next →
All datasetsen-esen-fres-enfr-enen-itMUSE en-deMUSE en-pt

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@184.26—Unverified
2Adv - Refine - CSLSP@181.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@182.94—Unverified
2Adv - Refine - CSLSP@182.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@183.5—Unverified
2Adv - Refine - CSLSP@183.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@183.23—Unverified
2Adv - Refine - CSLSP@182.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@181.45—Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@174.08—Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@184.65—Unverified